March 2013 Newsletter – Cluster Indicators

In this issue:

I. Commentary by Marge Sherald, CEO

II. NeuroShell Trader Super Computer has arrived

III. ZagTrader offers data and broker services for NeuroShell Trader

IV. Trading ETFs by Philippe Lonjoux, Noxa Analytics

V. Cluster Indicators

VI. How to stop this newsletter

***********************************************************

I. Commentary by Marge Sherald, CEO

1. We have two big announcements this month about the continuing evolution of NeuroShell Trader. First, we are releasing three different network versions of the Trader that substantially reduce the time required to optimize trading models. I’ve been testing it for several months and I promise that once you get used to this speed you won’t go back again. It really helps when you get an idea for a trading strategy and want to test it out. You create the “first draft” and run the test, and then you go back and tweak it. You get a lot more done in a shorter period of time. Details are below. The Pre-release pricing on the network versions lasts until March 31, 2013.

2. Second, we are very pleased to announce that we have added ZagTrader as one of our data providers and brokerage partners. They are currently supplying data for 70,000+ symbols at last count through the ZagTrader Bridge to NeuroShell Trader, which is available as part of the ZagTrader RT premium package. The data is provided by ESignal/interactive data through ZagTrader. In addition, they’ve built an interface between NeuroShell Trader and MetaTrader4 for trading FOREX, which is also included in the ZagTrader RT premium package. A lot of you have requested a link to MetaTrader4, so I suggest you check them out on www.zagtrader.com. Trades may be sent to an increasing number of brokers listed on their web site. Ask them about special offers for NeuroShell Trader users.

3. We also have an article by Philippe Lonjoux of Noxa Analytics that offers some valuable insight on how to trade Exchange Traded Funds (ETFs). This article should be of interest to a lot of you.

************************************************************

II. NeuroShell Trader Super Computer has arrived

Ward Systems Group is announcing the release of new versions of NeuroShell Trader that can distribute the optimization processing of complex financial models over your local area network. The result is a significant decrease in the amount of time it takes to create and update trading models as market conditions change.

Let’s say your local network has three computers attached, a 12 core machine and two quad core machines. That is a total of 20 cores, all of which can be searching for your optimum trading model simultaneously. The faster computers will handle a higher share of the load. You have control over which of the computers on the network you want to participate, and which you do not want to participate.

Choose from three different network versions depending on the power and speed you require. For example, the NeuroShell Trader Home Network version can distribute optimization processing to up to three computers on your network (and even to multiple cores/threads on each of those computers). The three computers include the server computer where you are running NeuroShell Trader and two additional computers that act as clients to the server computer.

The NeuroShell Trader Office Network version can distribute optimization processing across ten different computers and to the multiple cores/threads on each of those computers.

The NeuroShell Trader Corporate Network version ramps up the power to a max of 25 computers.

The resultant speed increase is dependent on the speed of the processors and clock speed on all computers as well as the overhead of controlling, setup, and communication with each distributed thread. It is recommended that network optimization only be used on larger trading models that have a larger number of parameters and which take more than a minute or two to optimize on a single computer. Smaller trading models can optimize more slowly across a network due to the control, setup and communications overhead and might not utilize all the available processing cores if more cores are available than needed for genetic optimization of smaller models.

Ward Systems Group is offering pre-release pricing of the NeuroShell Trader Network versions until March 31, 2013. In order to purchase any of the network versions of NeuroShell Trader, you must already own either the NeuroShell Trader® Power User or NeuroShell DayTrader® Power User for the server computer. Prices for the network versions listed below are in addition to the purchase price of either the NeuroShell Trader® Power User or NeuroShell DayTrader® Power User.

NeuroShell Trader Home Network (up to 3 computers) Upgrade price from Power User: $995.00 Pre-release Price: $ 796.00
NeuroShell Trader Office Network (up to 10 computers) Upgrade price from Power User: $2995.00 Pre-release price: $2396.00
NeuroShell Trader Corporate Network (up to 25 computers) Upgrade price from Power User: $7,495.00 Pre-release price: $5,996.00

To take advantage of this pre-release pricing, order only from the following web link: www.ward.net/60.asp or give us a call at 301 662 7950 or Skype us at wardsystems.

**********************************************************************

III. ZagTrader offers data and broker services for NeuroShell Trader

NeuroShell Trader can now connect to a new datafeed and trading partner named ZagTrader that includes coverage of a broad range of international markets, as well as major US stock indexes, futures, and FOREX.

ZagTrader offers a host of services including data, analysis, and connections to a wide variety of brokers. There are several different levels of premium packages of these services described on their web site. Go to www.zagtrader.com/home and click on the “Check how ZagTrader can benefit you” button to learn the details on each of the premium services. The ZagTrader premium packages provide value analysis, technical analysis, screeners, up to date market and company news, risk reports, and peer group analysis. You can take advantage of fundamental and technical analysis covering every single traded symbol.

No matter which premium service you choose, you can connect ZagTrader and NeuroShell Trader through either the ZagTrader Bridge program or the MT4 Bridge by ZagTrader. The ZagTrader Bridge data is provided by ESignal/interactive data and trades are sent to a variety of brokers linked in through ZagTrader. The MT4 Bridge by ZagTrader allows you to obtain data and trade Forex with MT4. Look under the Trading Tools Menu on ZagTrader.com which includes details on both the ZagTrader Bridge and the MT4 Bridge by ZagTrader.

The basic ZagTrader RT subscription is currently priced at $150 per month. If you sign up for an annual subscription, mention that you are a NeuroShell Trader user and get an extra 3 months added to your subscription for free!

Contact ZagTrader
North & South America: +1 (514) 661-1585 FREE
Europe, Middle East, Africa: +971-4-433-4385 FREE
http://www.zagtrader.com

***********************************************************************

IV. Trading ETFs by Philippe Lonjoux, Noxa Analytics

Embracing what is working now, and I say this without an ounce of cliché.

Exchanged-Traded Funds (ETFs) have never been so popular. Five ETFs including SPY featured in the top 10 most traded US securities by value in 2012. Their popularity is growing, in part because of their low costs. But I think there is another fundamental reason; simply because they work.

Leveraged ETFs for example; these index funds must rebalance their holdings on a daily basis to maintain their leverage targets. It has been estimated that for a market that has moved by one percent, the rebalancing may account for up to 16.8 percent of the total volume; it clearly serves as the “cardiac pump” for a trend that gathers substantial momentum near the close.

It is then possible to front-run this rebalancing to take advantage of the anticipated momentum. It has been reported* that, when the market has moved by at least 2 percent since the previous close, buying the index via its ETFs at 2:15 pm, and exiting at the close has generated annual returns higher than 100% between June 2006 and July 2011.

* Intraday Share Price Volatility and Leveraged ETF Rebalancing By E. Haryanto et Al., Nov. 2012

Unfortunately this opportunity is likely to be drying up as more momentum traders begin to drive the price up earlier in the day.

But it remains that ETF rebalancing will always account for some of the end-of-day share price volatility. This is precisely what AME is able to capitalize on when trading ETFs.

Check out the following web site for performance details:
https://www.box.com/s/donw6xruwti014p1jcit

We are currently offering a 20% discount on AME until March 31, 2013. To take advantage of this exciting deal:
http://neuroshell.noxapredict.com/en_products.htm

Happy trading.

Philippe Lonjoux
Noxa Analytics, Inc
p.*******@no*********.com

***********************************************************************

V. Cluster Indicators

If you use a visual approach to deciding whether the market is in an up trend or down trend, the Cluster Indicators Add-on may be an excellent tool for you to add to NeuroShell Trader. Say you look at the Commodity Channel Index and the MACD indicators on SPY, a stock you follow regularly. If you do this often enough, you probably have an idea about the location of those indicators on a chart and whether the market is in an up trend of a down trend. You could even plot the indicators on a scatter plot with CCI on the Y axis and MACD on the horizontal axis. If you have enough data you would begin to see clusters of each indictor and you could connect that cluster to an up trend or down trend. Once you have the values for that cluster of dots in mind you can look at the CCI and MACD values for the current bar and say I see an up trend coming. All of the data points don’t fall exactly on top of one another, but you can get a “feeling” for how far from the cluster center the new bar’s values are in order to be sure of your hunch. The bars that precede an up trend look somewhat similar, and the same is true for down trends. So far your visual system is working just fine. However, what happens when you want to look at five indicators? 16 indicators? Those can’t be plotted because you’d need a 16 dimensional scatter plot. But you can still measure how close the current bar is to a 16 dimensional cluster center. How about the added bonus feature of being able to tell the Trader which inputs are more important? Now you know why we designed the Cluster Indicators Add-on.

Note: Before you start trying to decide which 16 indicators to cluster, we want to remind you that using fewer inputs will more likely result in models that are more robust on out-of-sample data.

You can use cluster indicators in a trading strategy. For example a long entry rule would be “buy when the current bar is “close” enough to the cluster center of recent “buy” bars”. On the short side, you would sell “when the current bar is “close” enough to the sell cluster center”. The rules for both sides would be entered as “the cluster indicator < 0.5” and let the Trader’s optimizer find different values for the distance from the cluster center and for the input indicator parameters. We’ve updated one of the Cluster Add-on examples and it’s available for download from www.ward.net in the Examples section of the Cluster Indicators Add-on.

To learn more about the Cluster Indicators Add-on, visit www.NeuroShell.com, Product Info tab, and go to the Product Manuals section and look for Cluster Indicators.

You can save $100 if you purchase the Cluster Add-on before March 31, 2013. To buy Cluster for $199 rather than the list price of $299, order only from the following web link: www.ward.net/60.asp or give us a call at 301 662 7950 or Skype us at wardsystems.

***********************************************************************
VI. One way to stop this newsletter

It is really easy. Just change your E-mail address and don’t tell us.

***********************************************************************

Was this article helpful?

Related Articles